Render a Jw_cad drawing to a PNG image, with an optional bounding box in millimeters to zoom into a specific area.
Render a drawing to PNG and return the image (bbox in real mm to zoom).
| Name | Required | Description | Default |
|---|---|---|---|
| bbox | No | ||
| name | Yes | ||
| out_png | No | ||
| width_px | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that it returns an image (rare and useful) and that bbox zooms, but omits whether it's read-only, whether rendering can fail on large drawings, cost/latency, or what out_png does when set (write to disk? return path?). Multiple behavioral unknowns remain.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One efficient sentence that front-loads the core action and folds in the one parameter that needs explaining. No filler or repetition. Slightly under-specified rather than verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 4 params, 0% schema coverage, no annotations, and no output schema, the definition should explain parameters and return semantics. It only covers bbox/zoom and return type partially, leaving name, out_png, width_px, failures, and sibling distinctions unaddressed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. Only bbox is clarified ('in real mm to zoom'). 'name', 'out_png', and 'width_px' are undocumented in both description and schema — notably 'out_png' is ambiguous (output file path?) and 'width_px' defaults are invisible to the reader. Should do much more given the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific action (render to PNG) and names the resource (drawing), which is better than a tautology. But it doesn't distinguish 'drawing_preview' from siblings 'jww_preview' and 'gaihen_preview', and it's not clear from the description why a caller should choose this generic preview over the format-specific ones.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use guidance beyond the purpose clause. Nothing tells the agent when to use drawing_preview versus jww_preview/gaihen_preview, or when bbox is needed versus a full-page render. The only hint is that bbox zooms, which is indirectly a usage cue but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.